Investigating Location-Regularised Self-Supervised Feature Learning for Seafloor Visual Imagery

2025/09/08 by Cailei Liang, Adrian Bodenmann, Liang, Cailei +13 · 1 citation
Earth and Planetary Sciences · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Robotics (cs.RO) #Underwater Acoustics Research

paper · pdf · doi:10.48550/arxiv.2509.06660

openalex publication_date 2025/09/08 · openalex created_date 2025/10/11 · openalex updated_date 2026/07/28

Abstract

High-throughput interpretation of robotically gathered seafloor visual imagery can increase the efficiency of marine monitoring and exploration. Although recent research has suggested that location metadata can enhance self-supervised feature learning (SSL), its benefits across different SSL strategies, models and seafloor image datasets are underexplored. This study evaluates the impact of location-based regularisation on six state-of-the-art SSL frameworks, which include Convolutional Neural Network (CNN) and Vision Transformer (ViT) models with varying latent-space dimensionality. Evaluation across three diverse seafloor image datasets finds that location-regularisation consistently improves downstream classification performance over standard SSL, with average F1-score gains of 4.9 ± 4.0% for CNNs and 6.3 ± 8.9% for ViTs, respectively. While CNNs pretrained on generic datasets benefit from high-dimensional latent representations, dataset-optimised SSL achieves similar performance across the high (512) and low (128) dimensional latent representations. Location-regularised SSL improves CNN performance over pre-trained models by 2.7 ± 2.7% and 10.1 ± 9.4% for high and low-dimensional latent representations, respectively. For ViTs, high-dimensionality benefits both pre-trained and dataset-optimised SSL. Although location-regularisation improves SSL performance compared to standard SSL methods, pre-trained ViTs show strong generalisation, matching the best-performing location-regularised SSL with F1-scores of 0.795 ± 0.075 and 0.795 ± 0.077, respectively. The findings highlight the value of location metadata for SSL regularisation, particularly when using low-dimensional latent representations, and demonstrate strong generalisation of high-dimensional ViTs for seafloor image analysis.

Citations

• DenseDINO: Boosting Dense Self-Supervised Learning with Token-Based Point-Level Consistency
• DINOv2: Learning Robust Visual Features without Supervision
• GPT-4 Technical Report
• A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends
• Self-Supervised Learning with Data Augmentations Provably Isolates\n Content from Style
• Emerging Properties in Self-Supervised Vision Transformers
• Emerging Properties in Self-Supervised Vision Transformers
• Transformers in Vision: A Survey
• Exploring Simple Siamese Representation Learning
• Exploring Simple Siamese Representation Learning
• Unsupervised Learning of Dense Visual Representations
• A Survey on Contrastive Self-supervised Learning
• 3D CNN-PCA: A deep-learning-based parameterization for complex geomodels
• Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
• Self-supervised Learning: Generative or Contrastive
• Bootstrap your own latent: A new approach to self-supervised Learning
• A Simple Framework for Contrastive Learning of Visual Representations
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Momentum Contrast for Unsupervised Visual Representation Learning
• Momentum Contrast for Unsupervised Visual Representation Learning
• Deep Clustering for Unsupervised Learning of Visual Features
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Cited by

• Online Clustering of Seafloor Imagery for Interpretation during Long-Term AUV Operations

Related

• FathomNet: An underwater image training database for ocean exploration and discovery
• Reducing Label Dependency for Underwater Scene Understanding: A Survey of Datasets, Techniques and Applications
• On Vision Transformers for Classification Tasks in Side-Scan Sonar Imagery
• SeafloorAI: A Large-scale Vision-Language Dataset for Seafloor Geological Survey
• Self-Supervised Learning for Improved Synthetic Aperture Sonar Target Recognition